The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted source code, which serves as a vector for indirect prompt injection attacks.
Ingestion points: The skill processes user-provided code, pull requests, and diffs through instructions in the 'When to Use' and 'Review Process' sections.
Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between code to be reviewed and potential malicious instructions embedded in comments or string literals within that code.
Capability inventory: The skill utilizes tools like codecompass for semantic searching and refers to platform capabilities such as ast-analyzer, static-analyzer, and security-analyzer for deep code inspection.
Sanitization: The instructions do not specify any sanitization, filtering, or escaping mechanisms for the code being reviewed to prevent it from overriding the agent's behavior.

code-reviewer